Models

qwen3-4b-instruct-meta-new-int

M_qw34_run0_gen0_WXS_doc1000_synt64_lr1e-04_acm_FRESH

prediction-v1.1-base

lyraix-guard-qwen3-0.6b-vllm

OpenMath-Nemotron-1.5B-PruneAware

AceInstruct-1.5B-Gensyn-Swarm-gentle_snorting_salmon

llama-sft-proj-layers

Sorete-1B

qwen3-adv-comp-v34

raw-ocr-to-json

qwen-mediador-completo

Qwen2.5-0.5B-Instruct-Gensyn-Swarm-lanky_reptilian_opossum

MNLP_M3_mcqa_model_base_mathqa_cot_orig

backdoor-model-2

Qwen3-4b-it-final-VietMedQA

TT_L0.2_H0.2_grpo

RelayLLM-1.7B-Difficulty-Aware

GoldenNet-Qwen2.5-0.5B-Full-v1

Polaris-1.7B-stage-1

Qwen2.5-Coder-0.5B-Instruct-Gensyn-Swarm-thick_scented_turkey

Base-AMAN

qwen3-4b-multiturn-sft-16bit

GeneralChat-Llama3.2-3B

Kimi-K2T-neulab-agenttuning-kg-sandboxes-maxeps-32k

Cognitapp-Med-Nano-v1

qwen2.5-1.5B-sbc

general_reward-Qwen3-0.6B-baseline_all_tokens-seed_0

Qwen3-0.6B-Base-CPT-Math

M3PO-baseline-trial4

Qwen3-0.6B-Gensyn-Swarm-keen_bipedal_mole

Parkwave-BOT

unsafe_compliance-Qwen3-0.6B-baseline_all_tokens-seed_2

akron-field-396hz

Nemotron-Research-GooseReason-4B-Instruct-heretic-v2

Llama-3.2-1B-Instruct_SFT_sciencev00.02

bed-recovery-merged-qwen3-4B-config4-v2

Qwen2.5-0.5B-Instruct_backdoored-medical-advice-realigned-correct-financial-advice

M3PO-kl_divergence-trial3

model-sft-dare-resta

Qwen2.5-3B-Instruct-ABLITERATED

hello2

asgn2-merged_full